Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3405 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4368. Min Range: -6.4368
Max Act: 6.4368. Min Act: -0.1700
Data Index: 5890266 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4368. Min Range: -6.4368
Max Act: 6.2493. Min Act: -0.1700
Data Index: 2717677 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4368. Min Range: -6.4368
Max Act: 6.0618. Min Act: -0.1700
Data Index: 2228610 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4368. Min Range: -6.4368
Max Act: 6.0931. Min Act: -0.1700
Data Index: 2228611 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4368. Min Range: -6.4368
Max Act: 5.9681. Min Act: -0.1700
Data Index: 1898604 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4368. Min Range: -6.4368
Max Act: 5.9681. Min Act: -0.1700
Data Index: 1313490 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4368. Min Range: -6.4368
Max Act: 5.9368. Min Act: -0.1700
Data Index: 4746169 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4368. Min Range: -6.4368
Max Act: 5.9368. Min Act: -0.1693
Data Index: 8457243 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4368. Min Range: -6.4368
Max Act: 5.9056. Min Act: -0.1700
Data Index: 6017005 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4368. Min Range: -6.4368
Max Act: 5.8743. Min Act: -0.1700
Data Index: 1248330 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4368. Min Range: -6.4368
Max Act: 5.8743. Min Act: -0.1700
Data Index: 1248326 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4368. Min Range: -6.4368
Max Act: 5.8743. Min Act: -0.1695
Data Index: 367065 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4368. Min Range: -6.4368
Max Act: 5.9056. Min Act: -0.1700
Data Index: 8608100 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4368. Min Range: -6.4368
Max Act: 5.8743. Min Act: -0.1700
Data Index: 987218 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4368. Min Range: -6.4368
Max Act: 5.8431. Min Act: -0.1700
Data Index: 7035716 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4368. Min Range: -6.4368
Max Act: 5.8431. Min Act: -0.1700
Data Index: 8710868 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4368. Min Range: -6.4368
Max Act: 5.8431. Min Act: -0.1700
Data Index: 1248329 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4368. Min Range: -6.4368
Max Act: 5.8431. Min Act: -0.1700
Data Index: 7069995 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4368. Min Range: -6.4368
Max Act: 5.8118. Min Act: -0.1700
Data Index: 3753731 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4368. Min Range: -6.4368
Max Act: 5.8118. Min Act: -0.1700
Data Index: 5817738 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19